---
base_model: unsloth/Meta-Llama-3.1-8B-bnb-4bit
library_name: peft
---

**Overview**

DerivationGeneration8B is a QLoRA fine-tuned from a quantised LLaMa-3.1-8B checkpoint on 15K (LaTeX) synthetic mathematical derivations (containing 4 - 10 equations) via a custom [script](https://github.com/jmeadows17/deriving-equations-with-LLMs/blob/main/llama_3.1_qlora_sft.py) using ROUGE as the validation metric for early stopping (total 6 epochs). This approach outperforms [MathT5](https://huggingface.co./jmeadows17/MathT5-large) in both in-distribution and perturbed evaluation cases presented in [related work](https://arxiv.org/abs/2307.09998).

**How to use**

A notebook for inference is available [here](https://github.com/jmeadows17/deriving-equations-with-LLMs/blob/main/llama_evaluation.ipynb). The model was exposed to prompts through the chatml template (all in the notebook).

**Example prompt**

```prompt = "Given \\cos{(q)} = \\theta{(q)}, then derive - \\sin{(q)} = \\frac{d}{d q} \\theta{(q)}, then obtain (- \\sin{(q)})^{q} (\\frac{d}{d q} \\cos{(q)})^{q} = (- \\sin{(q)})^{2 q}"```

- PEFT 0.12.0